© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128051
    Prev
    Next
    INDEX
    Explanations

    noting observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.68
    tyfik
    -1.55
    爍
    -1.42
     epitome
    -1.38
    ovsk
    -1.38
    𐌽
    -1.36
    ulism
    -1.34
    ulauan
    -1.34
    言うと
    -1.34
     unwit
    -1.31
    POSITIVE LOGITS
     that
    3.17
     the
    2.75
    '
    1.67
     destaca
    1.65
    赑
    1.58
    寕
    1.57
    hibited
    1.56
     '
    1.55
     erano
    1.54
     ficam
    1.54
    Activations Density 0.012%

    No Known Activations